Task control in generative artificial intelligence based on prompt processing units

Abstract

In one implementation, a device may identify a type of task and its context indicated by a prompt sent by a user for input to a language model. The device may authorize the prompt for input to the language model based on the type of task and its context. The device may make a determination as to whether a response of the language model to the prompt is authorized to be returned to the user based on the response, the type of task, and its context. The device may prevent the response from being returned to the user when the determination indicates that the response is not authorized to be returned.

What is claimed is: 
     
         1 . A method, comprising:
 identifying, by a device, a type of task and its context indicated by a prompt sent by a user for input to a language model;   authorizing, by the device, the prompt for input to the language model based on the type of task and its context;   making, by the device, a determination as to whether a response of the language model to the prompt is authorized to be returned to the user based on the response, the type of task, and its context; and   preventing, by the device, the response from being returned to the user when the determination indicates that the response is not authorized to be returned.   
     
     
         2 . The method as in  claim 1 , wherein control over the prompt is retained by an intermediate layer prior to sending the prompt to its input to the language model. 
     
     
         3 . The method as in  claim 1 , wherein control over the response of the language model to the prompt is retained by an intermediate layer while making the determination as to whether the response of the language model to the prompt is authorized to be returned to the user. 
     
     
         4 . The method as in  claim 1 , further comprising:
 making a determination as to whether the prompt is authorized for the input to the language model based on a comparison of the type of task and its context to a task control policy.   
     
     
         5 . The method as in  claim 4 , further comprising:
 blocking the prompt from being input to the language model when the type of task and its context violate the task control policy.   
     
     
         6 . The method as in  claim 4 , further comprising:
 causing the prompt to be reengineered prior to being input to the language model when the type of task and its context violate the task control policy.   
     
     
         7 . The method as in  claim 1 , further comprising:
 logging a task control policy violation associated with the prompt.   
     
     
         8 . The method as in  claim 1 , further comprising:
 generating, based on logs of task control policy violations, characterizations of task control policy violations across a plurality of prompts.   
     
     
         9 . The method as in  claim 1 , further comprising:
 parsing the prompt to generate a prompt characterization, wherein the prompt characterization includes an indication of the type of the task.   
     
     
         10 . The method as in  claim 1 , wherein the context includes a file from a retrieval-augmented generation system. 
     
     
         11 . An apparatus, comprising:
 one or more network interfaces;   a processor coupled to the one or more network interfaces and configured to execute one or more processes; and   a memory configured to store a process that is executable by the processor, the process when executed configured to:
 identify a type of task and its context indicated by a prompt sent by a user for input to a language model; 
 authorize the prompt for input to the language model based on the type of task and its context; 
 make a determination as to whether a response of the language model to the prompt is authorized to be returned to the user based on the response, the type of task, and its context; and 
 prevent the response from being returned to the user when the determination indicates that the response is not authorized to be returned. 
   
     
     
         12 . The apparatus as in  claim 11 , wherein control over the prompt is retained by an intermediate layer prior to sending the prompt to its input to the language model. 
     
     
         13 . The apparatus as in  claim 11 , wherein control over the response of the language model to the prompt is retained by an intermediate layer while making the determination as to whether the response of the language model to the prompt is authorized to be returned to the user. 
     
     
         14 . The apparatus as in  claim 11 , the process when executed further configured to:
 make a determination as to whether the prompt is authorized for the input to the language model based on a comparison of the type of task and its context to a task control policy.   
     
     
         15 . The apparatus as in  claim 14 , the process when executed further configured to:
 block the prompt from being input to the language model when the type of task and its context violate the task control policy.   
     
     
         16 . The apparatus as in  claim 14 , the process when executed further configured to:
 cause the prompt to be reengineered prior to being input to the language model when the type of task and its context violate the task control policy.   
     
     
         17 . The apparatus as in  claim 11 , the process when executed further configured to:
 log a task control policy violation associated with the prompt.   
     
     
         18 . The apparatus as in  claim 11 , the process when executed further configured to:
 generate, based on logs of task control policy violations, characterizations of task control policy violations across a plurality of prompts.   
     
     
         19 . The apparatus as in  claim 11 , the process when executed further configured to:
 parse the prompt to generate a prompt characterization, wherein the prompt characterization includes an indication of the type of the task.   
     
     
         20 . A tangible, non-transitory, computer-readable medium storing program instructions that cause a device to execute a process comprising:
 identifying a type of task and its context indicated by a prompt sent by a user for input to a language model;   authorizing the prompt for input to the language model based on the type of task and its context;   making a determination as to whether a response of the language model to the prompt is authorized to be returned to the user based on the response, the type of task, and its context; and   preventing the response from being returned to the user when the determination indicates that the response is not authorized to be returned.